Borrowing it
Nothing to install: this file belongs to mihai-dulgheru/mssql-mcp-node. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mihai-dulgheru/mssql-mcp-node/master/CLAUDE.mdgit clone --depth 1 https://github.com/mihai-dulgheru/mssql-mcp-nodeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/mihai-dulgheru/mssql-mcp-node/claude-md)<a href="https://agentmods.dev/instructions/mihai-dulgheru/mssql-mcp-node/claude-md"><img src="https://agentmods.dev/badge/instructions/mihai-dulgheru/mssql-mcp-node/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mihai-dulgheru/mssql-mcp-node/claude-md"><img src="https://agentmods.dev/badge/instructions/mihai-dulgheru/mssql-mcp-node/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01656 | $0.01656 |
| Opus 5 | $0.00828 | $0.00828 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
mssql-mcp-node CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
mssql-mcp-node is an npm-published MCP server (CommonJS, Node ≥ 18, no build step) that exposes one or more Microsoft SQL Server databases to MCP clients via 11 tools, a CSV table resource template, and two prompts. It runs over stdio (src/index.js, also the bin) or stateless Streamable HTTP (src/http.js, POST /mcp). README.md is the user-facing reference (tool catalog, env vars, security model) and must be updated when tools or env vars change.
Commands
npm test # all unit tests (node --test, no DB needed)
node --test test/safety.test.js # one file
node --test --test-name-pattern="rollback" test/safety.test.js # one test by name
npx eslint . # lint (no npm script for this)
npx prettier --check . # format check; --write to fix
npm run smoke # wire-level HTTP+stdio test with fake creds, no DB (scripts/smoke.js)
MSSQL_TEST_PASSWORD='...' npm run integration # real SQL Server; creates+drops mcp_test_<ts> (see scripts/integration.js header for Docker one-liner)
npm start / npm run dev # stdio (dev = nodemon)
npm run start:http / npm run dev:http # HTTP on $PORT (default 3000)
npx @modelcontextprotocol/inspector node src/index.js # interactive e2e
Server needs MSSQL_* env (single-db) or MSSQL_<NAME>_* (multi-db) — see .env.example. .env is gitignored and loaded via dotenv in both entry points.
Architecture
Request flow: entry point → createServer() in src/server.js → tools/resources/prompts.registerAll(server). The HTTP entry creates a fresh McpServer + transport per POST (stateless mode); stdio creates one for the process lifetime. Both close all pools on SIGINT/SIGTERM.
Tool module contract. Every file in src/tools/ exports { name, config, handler } where config is the registerTool config (title, description, Zod inputSchema/outputSchema shapes, annotations). src/tools/index.js is an explicit array, not a directory scan — a new tool must be added there. Handlers all follow the same shape:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 64 lines · 1,656 tokens per session scan A 451303179910
mssql-mcp-node CLAUDE.md is an instructions file published in the GitHub repository mihai-dulgheru/mssql-mcp-node (4 stars, last pushed yesterday), licensed MIT. It adds 1,656 tokens to every session, about $0.0083 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).